Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lac5q/beastmode --skill effectivenessgit clone --depth 1 https://github.com/lac5q/beastmodeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lac5q/beastmode/effectiveness)<a href="https://agentmods.dev/skills/lac5q/beastmode/effectiveness"><img src="https://agentmods.dev/badge/skills/lac5q/beastmode/effectiveness/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lac5q/beastmode/effectiveness"><img src="https://agentmods.dev/badge/skills/lac5q/beastmode/effectiveness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.01131 |
| Opus 5.5 | $0.00011 | $0.00452 |
| Sonnet 5.5 | $0.00006 | $0.00226 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
beastmode-effectiveness-evaluation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- driver.py 12 KB runs code
- environment.json 1.2 KB
- fixtures/task01/mutants.json 534 B
- fixtures/task01/private_cases.json 4.7 KB
- fixtures/task01/public_examples.json 781 B
- fixtures/task01/public.md 1.6 KB
- fixtures/task01/reference.py 2.8 KB runs code
- fixtures/task02/mutants.json 474 B
- fixtures/task02/private_cases.json 5.2 KB
- fixtures/task02/public_examples.json 940 B
- fixtures/task02/public.md 1.6 KB
- fixtures/task02/reference.py 2.9 KB runs code
- fixtures/task03/mutants.json 666 B
- fixtures/task03/private_cases.json 2.7 KB
- fixtures/task03/public_examples.json 520 B
- fixtures/task03/public.md 1.4 KB
- fixtures/task03/reference.py 1.5 KB runs code
- fixtures/task04/mutants.json 691 B
- fixtures/task04/private_cases.json 3.7 KB
- fixtures/task04/public_examples.json 621 B
- fixtures/task04/public.md 1.3 KB
- fixtures/task04/reference.py 1.5 KB runs code
- fixtures/task05/mutants.json 896 B
- fixtures/task05/private_cases.json 5.1 KB
- fixtures/task05/public_examples.json 1013 B
- fixtures/task05/public.md 1.8 KB
- fixtures/task05/reference.py 2.2 KB runs code
- fixtures/task06/mutants.json 782 B
- fixtures/task06/private_cases.json 5.8 KB
- fixtures/task06/public_examples.json 1.2 KB
- fixtures/task06/public.md 2.0 KB
- fixtures/task06/reference.py 3.0 KB runs code
- fixtures/task07/mutants.json 1.7 KB
- fixtures/task07/private_cases.json 6.9 KB
- fixtures/task07/public_examples.json 1.9 KB
- fixtures/task07/public.md 2.0 KB
- fixtures/task07/reference.py 2.8 KB runs code
- fixtures/task08/mutants.json 1.4 KB
- fixtures/task08/private_cases.json 6.3 KB
- fixtures/task08/public_examples.json 1.5 KB
- fixtures/task08/public.md 2.1 KB
- fixtures/task08/reference.py 3.2 KB runs code
- fixtures/task09/mutants.json 799 B
- fixtures/task09/private_cases.json 2.8 KB
- fixtures/task09/public_examples.json 499 B
- fixtures/task09/public.md 2.1 KB
- fixtures/task09/reference.py 5.3 KB runs code
- fixtures/task10/mutants.json 1.3 KB
- fixtures/task10/private_cases.json 5.9 KB
- fixtures/task10/public_examples.json 1.2 KB
- fixtures/task10/public.md 2.2 KB
- fixtures/task10/reference.py 3.8 KB runs code
- fixtures/task11/mutants.json 1.1 KB
- fixtures/task11/private_cases.json 4.7 KB
- fixtures/task11/public_examples.json 847 B
- fixtures/task11/public.md 1.4 KB
- fixtures/task11/reference.py 2.2 KB runs code
- fixtures/task12/mutants.json 1.4 KB
- fixtures/task12/private_cases.json 6.0 KB
- fixtures/task12/public_examples.json 1.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed · +20 lines 06687974edc7
- 1mo ago First seen · 39 lines · 28 tokens per session scan A 3a5d1058be8a
beastmode-effectiveness-evaluation is a skill published in the GitHub repository lac5q/beastmode (20 stars, last pushed 21d ago), with no licence file. It adds 28 tokens to every session and 1,131 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-13.
Other skills, from other repositories
kungfu-agent-onboarding
Discover the exact Kungfu Project, WorkConsole, WorkRef, Skill catalog, and Core Work state admitted to this Amp process.
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
beevibe-team-mesh-negotiation
Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…
beevibe-verify-pr
CI verification before marking a PR-bearing task done. Use BEFORE calling mcpbeevibeupdateprogress(done) on any session whose deliverable is a pull request — including the first dispatch (you opened the PR with gh pr create) and any revision dispatch (you pushed new commits to an existing PR). Watches the PR's…
beevibe-use-repo
You are the child agent inside a fresh Docker sandbox. Borrow the given GitHub repo, produce a real artifact for the goal, and export it. Do not review the repo. The proof is that it works.
skills-constitution
A set of rules that makes an agent check its memory and available skills before handling professional tasks such as coding, file work, data analysis, or deployment.